MM 2012 Proceedings

Kiyoharu Aizawa, Noboru Babaguchi, John R. Smith (Eds.), Proceedings of the 2012 ACM Multimedia Conference, MM '12, October 29�November 2, 2012, Nara, Japan. ACM 2012, ISBN 978-1-4503-1589-5.

Table of Contents

Message from the General Chairs
Kiyoharu Aizawa (The University of Tokyo)
Noboru Babaguchi (Osaka University)
John R. Smith (IBM T.J. Watson Research Center)

Message from the Technical Program Chairs
Shin'ichi Satoh (National Institute of Informatics)
Thomas Plagemann (University of Oslo)
Xian-Sheng Hua (Microsoft)
Rong Yan (Facebook)

Message from the ACM SIGMM Chair
Klara Nahrstedt (University of Ilinois at Urbana-Champaign)

MM 2012 Conference Organization

MM 2012 Technical Program Area Chairs

MM 2012 Technical Program Committee

MM 2012 Additional Reviewers

MM 2012 Technical Demo Program Committee

MM 2012 Brave New Ideas Program Committee

MM 2012 Doctoral Symposium Committee

MM 2012 Sponsor & Supporters

Full Paper Session 1: Content-Based Image Retrieval
Session Chair: Benoit Huet (EURECOM)

A Bag-of-Objects Retrieval Model for Web Image Search (Page 49)
Yang Yang (Nanjing University & Microsoft Research Asia)
Linjun Yang (Microsoft Research Asia)
Gangshan Wu (Nanjing University)
Shipeng Li (Microsoft Research Asia)

Harvesting Visual Concepts for Image Search with Complex Queries (Page 59)
Liqiang Nie (National University of Singapore)
Shuicheng Yan (National University of Singapore)
Meng Wang (Hefei University of Technology)
Richang Hong (Hefei University of Technology)
Tat-Seng Chua (National University of Singapore)

Exploiting Visual Word Co-occurrence for Image Retrieval (Page 69)
Miaojing Shi (Peking University)
Xinghai Sun (Peking University)
Dacheng Tao (University of Technology)
Chao Xu (Peking University)

Attribute Feedback (Page 79)
Hanwang Zhang (National University of Singapore)
Zheng-Jun Zha (National University of Singapore)
Shuicheng Yan (National University of Singapore)
Jingwen Bian (National University of Singapore)
Tat-Seng Chua (National University of Singapore)

Full Paper Session 2: Audio and Music
Session Chair: Gerald Friedland (ICSI and University of California, Berkeley)

The Acoustic Emotion Gaussians Model for Emotion-Based Music Annotation and Retrieval (Page 89)
Ju-Chiang Wang (National Taiwan University & Academia Sinica)
Yi-Hsuan Yang (Academia Sinica)
Hsin-Min Wang (Academia Sinica)
Shyh-Kang Jeng (National Taiwan University)

Context-Aware Mobile Music Recommendation for Daily Activities (Page 99)
Xinxi Wang (National University of Singapore)
David Rosenblum (National University of Singapore)
Ye Wang (National University of Singapore)

MusicScore: Mobile Music Composition for Practice and Fun (Page 109)
Zimu Liu (University of Toronto)
Yuan Feng (University of Toronto)
Baochun Li (University of Toronto)

Modeling the QoE of Rate Changes in SKYPE/SILK VoIP Calls (Page 119)
Chien-nan Chen (National Taiwan University)
Cing-yu Chu (National Taiwan University)
Su-ling Yeh (National Taiwan University)
Hao-hua Chu (National Taiwan University)
Polly Huang (National Taiwan University)

Full Paper Session 3: Video Applications
Session Chair: Alexander G. Hauptmann (Carnegie Mellon University)

PaperVideo: Interacting with Videos on Multiple Paper-like Displays (Page 129)
Roman Lissermann (Technische Universit�t Darmstadt)
Simon Olberding (Massachusetts Institute of Technology)
Benjamin Petry (Technische Universit�t Darmstadt)
Max M�hlh�user (Technische Universit�t Darmstadt)
J�rgen Steimle (Massachusetts Institute of Technology)

MoViMash: Online Mobile Video Mashup (Page 139)
Mukesh Saini (National University of Singapore)
Raghudeep Gadde (National University of Singapore)
Shuicheng Yan (National University of Singapore)
Wei Tsang Ooi (National University of Singapore)

An Interactive System of Stereoscopic Video Conversion (Page 149)
Zhebin Zhang (Peking University)
Chen Zhou (Peking University)
Bo Xin (Peking University)
Yizhou Wang (Peking University)
Wen Gao (Peking University)

Enabling "Togetherness" in High-Quality Domestic Video Conferencing (Page 159)
Ian Kegel (BT Research & Technology)
Pablo Cesar (Centrum Wiskunde & Informatica)
Jack Jansen (Centrum Wiskunde & Informatica)
Dick Bulterman (Centrum Wiskunde & Informatica)
Tim Stevens (BT Research & Technology)
Joke Kort (TNO ICT)
Nikolaus F�rber (Fraunhofer IIS)

Full Paper Session 4: Large Scale Search
Session Chair: Chong-Wah Ngo (City University of Hong Kong)

Scalar Quantization for Large Scale Image Search (Page 169)
Wengang Zhou (University of Texas at San Antonio)
Yijuan Lu (Texas State University)
Houqiang Li (University of Science and Technology of China)
Qi Tian (University of Texas at San Antonio)

Query-Driven Iterated Neighborhood Graph Search for Large Scale Indexing (Page 179)
Jingdong Wang (Microsoft Research Asia)
Shipeng Li (Microsoft Research Asia)

SymCity: Feature Selection by Symmetry for Large Scale Image Retrieval (Page 189)
Giorgos Tolias (National Technical University of Athens)
Yannis Kalantidis (National Technical University of Athens)
Yannis Avrithis (National Technical University of Athens)

Embedding Spatial Context Information into Inverted File for Large-Scale Image Retrieval (Page 199)
Zhen Liu (University of Science and Technology of China)
Houqiang Li (University of Science and Technology of China)
Wengang Zhou (University of Texas at San Antonio)
Qi Tian (University of Texas at San Antonio)

Full Paper Session 5: Person and Face Analysis
Session Chair: Nicu Sebe (University of Trento)

A Smile Can Reveal Your Age: Enabling Facial Dynamics in Age Estimation (Page 209)
Hamdi Dibeklioğlu (University of Amsterdam)
Theo Gevers (University of Amsterdam)
Albert Ali Salah (Bogazi�i University)
Roberto Valenti (University of Amsterdam)

Unsupervised Face-Name Association via Commute Distance (Page 219)
Jiajun Bu (Zhejiang University)
Bin Xu (Zhejiang University)
Chenxia Wu (Zhejiang University)
Chun Chen (Zhejiang University)
Jianke Zhu (Zhejiang University)
Deng Cai (Zhejiang University)
Xiaofei He (Zhejiang University)

On Shape and the Computability of Emotions (Page 229)
Xin Lu (The Pennsylvania State University)
Poonam Suryanarayan (The Pennsylvania State University)
Reginald B. Adams Jr. (The Pennsylvania State University)
Jia Li (The Pennsylvania State University)
Michelle G. Newman (The Pennsylvania State University)
James Z. Wang (The Pennsylvania State University)

Sense Beauty via Face, Dressing, and/or Voice (Page 239)
Tam V. Nguyen (National University of Singapore)
Si Liu (National Laboratory of Pattern Recognition)
Bingbing Ni (Advanced Digital Sciences Center)
Jun Tan (National University of Defense Technology)
Yong Rui (Microsoft Research Asia)
Shuicheng Yan (National University of Singapore)

Full Paper Session 6: Video Distribution
Session Chair: Nalini Venkatasubrahanian (University of California, Irvine)

Leveraging Social Network Concepts for Efficient Peer-to-Peer Live Streaming Systems (Page 249)
Haiying Shen (Clemson University)
Ze Li (Clemson University)
Hailang Wang (Clemson University)
JIn Li (Microsoft Research)

Jetway: Minimizing Costs on Inter-Datacenter Video Traffic (Page 259)
Yuan Feng (University of Toronto)
Baochun Li (University of Toronto)
Bo Li (Hong Kong University of Science and Technology)

Control of Distributed Servers for Quality-Fair Delivery of Multiple Video Streams (Page 269)
Nesrine Changuel (Alcatel-Lucent Bell Labs)
Bessem Sayadi (Alcatel-Lucent Bell Labs)
Michel Kieffer (University of Paris-Sud)

GreenTube: Power Optimization for Mobile Videostreaming via Dynamic Cache Management (Page 279)
Xin Li (George Mason University)
Mian Dong (Samsung Telecommunications America)
Zhan Ma (Samsung Telecommunications America)
Felix Fernandes (Samsung Telecommunications America)

Full Paper Session 7: Visual Search
Session Chair: Qi Tian (University of Texas at San Antonio)

A Multimedia Analytics Framework for Browsing Image Collections in Digital Forensics (Page 289)
Marcel Worring (University of Amsterdam)
Andreas Engl (University of Amsterdam)
Camelia Smeria (University of Amsterdam)

Submodular Video Hashing: A Unified Framework Towards Video Pooling and Indexing (Page 299)
Liangliang Cao (IBM T.J. Watson Research Center)
Zhenguo Li (Columbia University)
Yadong Mu (Columbia University)
Shih-Fu Chang (Columbia University)

Exploratory Search of Long Surveillance Videos (Page 309)
Greg Casta��n (Boston University)
Venkatesh Saligrama (Boston University)
Andr� Louis Caron (Universit� de Sherbrooke)
Pierre-Marc Jodoin (Universit� de Sherbrooke)

When Video Search Goes Wrong: Predicting Query Failure Using Search Engine Logs and Visual Search Results (Page 319)
Christoph Kofler (Delft University of Technology)
Linjun Yang (Microsoft Research Asia)
Martha Larson (Delft University of Technology)
Tao Mei (Microsoft Research Asia)
Alan Hanjalic (Delft University of Technology)
Shipeng Li (Microsoft Research Asia)

Full Paper Session 8: Human-centric Media
Session Chair: Frank Nack (University of Amsterdam)

Don't Ask Me What I'm Like, Just Watch and Listen (Page 329)
Ruchir Srivastava (National University of Singapore)
Jiashi Feng (National University of Singapore)
Sujoy Roy (Institute for Infocomm Research)
Shuicheng Yan (National University of Singapore)
Terence Sim (National University of Singapore)

Controlling Urban Lighting by Human Motion Patterns Results from a Full Scale Experiment (Page 339)
Esben Skouboe Poulsen (Aalborg University)
Hans J�rgen Andersen (Aalborg University)
Ole B. Jensen (Aalborg University)
Rikke Gade (Aalborg University)
Tobias Thyrrestrup (Aalborg University)
Thomas B. Moeslund (Aalborg University)

In the Eye of the Beholder: Employing Statistical Analysis and Eye Tracking for Analyzing Abstract Paintings (Page 349)
Victoria Yanulevskaya (University of Trento)
Jasper Uijlings (University of Trento)
Elia Bruni (University of Trento)
Andreza Sartori (University of Trento & Telecom Italia - SKIL)
Elisa Zamboni (University of Trento)
Francesca Bacci (Museum of Art of Trento and Rovereto)
David Melcher (University of Trento)
Nicu Sebe (University of Trento)

Online Crowdsourcing Subjective Image Quality Assessment (Page 359)
Qianqian Xu (Chinese Academy of Sciences)
Qingming Huang (Chinese Academy of Sciences)
Yuan Yao (Peking University)

Full Paper Session 9: Presentation and Organization
Session Chair: Heng Tao Shen (The University of Queensland)

Image Colorization Using Similar Images (Page 369)
Raj Kumar Gupta (Nanyang Technological University)
Alex Yong-Sang Chia (Institute for Infocomm Research)
Deepu Rajan (Nanyang Technological University)
Ee Sin Ng (Institute for Infocomm Research)
Huang Zhiyong (Institute for Infocomm Research)

Semi-Automated Magazine Layout Using Content-Based Image Features (Page 379)
Mikko Kuhna (Aalto University)
Ida-Maria Kivel� (Aalto University)
Pirkko Oittinen (Aalto University)

Understanding Screen Contents for Building a High Performance, Real Time Screen Sharing System (Page 389)
Surendar Chandra (FX Palo Alto Laboratory Inc.)
Jacob T. Biehl (FX Palo Alto Laboratory Inc.)
John Boreczky (FX Palo Alto Laboratory Inc.)
Scott Carter (FX Palo Alto Laboratory Inc.)
Lawrence A. Rowe (FX Palo Alto Laboratory Inc.)

El-pincel - A Painter Cloud Service for Greener Web Pages (Page 399)
Bhojan Anand (National University of Singapore)
Lee Kee Chong (National University of Singapore)
Ee-Chien Chang (National University of Singapore)
Mun Choon Chan (National University of Singapore)
Ananda L. Akkihebbal (National University of Singapore)
Wei Tsang Ooi (National University of Singapore)

Full Paper Session 10: Haptics
Session Chair: Yuichi Nakamura (Kyoto University)

Low Bitrate Source-Filter Model Based Compression of Vibrotactile Texture Signals in Haptic Teleoperation (Page 409)
Rahul Chaudhari (Technische Universit�t M�nchen)
Burak �izmeci (Technische Universit�t M�nchen)
Katherine J. Kuchenbecker (University of Pennsylvania)
Seungmoon Choi (POSTECH)
Eckehard Steinbach (Technische Universit�t M�nchen)

Vibrotactile Feedback of Motor Performance Errors for Enhancing Motor Learning (Page 419)
Troy McDaniel (Arizona State University)
Morris Goldberg (Arizona State University)
Shantanu Bala (Arizona State University)
Bijan Fakhri (Arizona State University)
Sethuraman Panchanathan (Arizona State University)

MOGAT: Mobile Games with Auditory Training for Children with Cochlear Implants (Page 429)
Yinsheng Zhou (National University of Singapore)
Khe Chai Sim (National University of Singapore)
Patsy Tan (Singapore General Hospital)
Ye Wang (National University of Singapore)

Full Paper Session 11: Event Recognition
Session Chair: Ansgar Scherp (University of Koblenz-Landau)

Visual Knowledge Transfer Among Multiple Cameras for People Counting with Occlusion Handling (Page 439)
Ming-Fang Weng (Academia Sinica)
Yen-Yu Lin (Academia Sinica)
Nick C. Tang (Academia Sinica)
Hong-Yuan Mark Liao (Academia Sinica)

Leveraging High-Level and Low-Level Features for Multimedia Event Detection (Page 449)
Lu Jiang (Carnegie Mellon University)
Alexander G. Hauptmann (Carnegie Mellon University)
Guang Xiang (Carnegie Mellon University)

Interactive Data-Driven Discovery of Temporal Behavior Models from Events in Media Streams (Page 459)
Chreston Miller (Virginia Tech)
Francis Quek (Virginia Tech)

Knowledge Adaptation for Ad Hoc Multimedia Event Detection with Few Exemplars (Page 469)
Zhigang Ma (University of Trento)
Yi Yang (Carnegie Mellon University)
Yang Cai (Carnegie Mellon University)
Nicu Sebe (University of Trento)
Alexander G. Hauptmann (Carnegie Mellon University)

Full Paper Session 12: Semantic Tagging
Session Chair: Lexing Xie (Australian National University)

Multi-View Learning from Imperfect Tagging (Page 479)
Zhongang Qi (Zhejiang University)
Ming Yang (Zhejiang University)
Zhongfei (Mark) Zhang (Zhejiang University)
Zhengyou Zhang (Microsoft Research)

Joint Statistical Analysis of Images and Keywords with Applications in Semantic Image Enhancement (Page 489)
Albrecht Lindner (�cole Polytechnique F�d�rale de Lausanne)
Appu Shaji (�cole Polytechnique F�d�rale de Lausanne)
Nicolas Bonnier (Oc� Print Logic Technologies)
Sabine S�sstrunk (�cole Polytechnique F�d�rale de Lausanne)

Image Annotation by Semantic Sparse Recoding of Visual Content (Page 499)
Zhiwu Lu (Peking University)
Yuxin Peng (Peking University)

Annotating Web Images Using NOVA: NOn-conVex group spArsity (Page 509)
Fei Wu (Zhejiang University)
Ying Yuan (Zhejiang University)
Yong Rui (Microsoft Research Asia)
Shuicheng Yan (Department of Electrical and Computer Engineering, NUS)
Yueting Zhuang (Zhejiang University)

Full Paper Session 13: Image Analysis
Session Chair: Shuicheng Yan (National University of Singapore)

Query-Adaptive Shape Topic Mining for Hand-Drawn Sketch Recognition (Page 519)
Zhenbang Sun (Shanghai Jiao Tong University)
Changhu Wang (Microsoft Research Asia)
Liqing Zhang (Shanghai Jiao Tong University)
Lei Zhang (Microsoft Research Asia)

Correlated Attribute Transfer with Multi-Task Graph-Guided Fusion (Page 529)
Yahong Han (Tianjin University)
Fei Wu (Zhejiang University)
Xinyan Lu (Zhejiang University)
Qi Tian (University of Texas at San Antonio)
Yueting Zhuang (Zhejiang University)
Jiebo Luo (University of Rochester)

Spatial Pooling of Heterogeneous Features for Image Applications (Page 539)
Lingxi Xie (Tsinghua University)
Qi Tian (University of Texas at San Antonio)
Bo Zhang (Tsinghua University)

Efficient Image Annotation for Automatic Sentence Generation (Page 549)
Yoshitaka Ushiku (The University of Tokyo)
Tatsuya Harada (The University of Tokyo & JST PRESTO)
Yasuo Kuniyoshi (The University of Tokyo)

Full Paper Session 14: Mobile Systems
Session Chair: Vera Goebel (University of Oslo)

Dinner of Luci�rnaga: An Interactive Play with iPhone App in Theater (Page 559)
Yu-Chuan Tseng (Shih Hsin University)
Kuan-Ying Wu (National Chiao Tung University)
Yi-Ching Huang (National Taiwan University)
Chi-Ping Chin (MUTIENLIAO Interactive dot TW)

Accelerating SURF Detector on Mobile Devices (Page 569)
Xin Yang (University of California, Santa Barbara)
Kwang-Ting (Tim) Cheng (University of California, Santa Barbara)

IMShare: Instantly Sharing Your Mobile Landmark Images by Search-based Reconstruction (Page 579)
Lican Dai (University of Science and Technology of China)
Huanjing Yue (Tianjin University)
Xiaoyan Sun (Microsoft Research Asia)
Feng Wu (Microsoft Research Asia)

Discovering Areas of Interest with Geo-tagged Images and Check-ins (Page 589)
Jiajun Liu (The University of Queensland)
Zi Huang (The University of Queensland)
Lei Chen (Hong Kong University of Science and Technology)
Heng Tao Shen (The University of Queensland)
Zhixian Yan (�cole Polytechnique F�d�rale de Lausanne)

Full Paper Session 15: Image Content Analysis
Session Chair: Winston Hsu (National Taiwan University)

Scalable Mining of Small Visual Objects (Page 599)
Pierre Letessier (INA & INRIA Sophia-Antipolis)
Olivier Buisson (INA)
Alexis Joly (INRIA Sophia-Antipolis)

Snap-and-Ask: Answering Multimodal Question by Naming Visual Instance (Page 609)
Wei Zhang (City University of Hong Kong)
Lei Pang (City University of Hong Kong)
Chong-Wah Ngo (City University of Hong Kong)

"Hi, Magic Closet, Tell Me What to Wear!" (Page 619)
Si Liu (National University of Singapore & Chinese Academy of Sciences)
Jiashi Feng (National University of Singapore)
Zheng Song (National University of Singapore)
Tianzhu Zhang (Advanced Digital Sciences Center)
Hanqing Lu (Chinese Academy of Sciences)
Changsheng Xu (Chinese Academy of Sciences)
Shuicheng Yan (National University of Singapore)

Constraint-Optimized Keypoint Inhibition/Insertion Attack: Security Threat to Scale-Space Image Feature Extraction (Page 629)
Chun-Shien Lu (Academia Sinica)
Chao-Yung Hsu (Academia Sinica)

Full Paper Session 16: Social Media
Session Chair: Bernard Merialdo (Institut EURECOM)

Mining In-Class Social Networks for Large-Scale Pedagogical Analysis (Page 639)
Xiao-Yong Wei (Sichuan University)
Zhen-Qun Yang (Sichuan University)

SocialTransfer: Cross-Domain Transfer Learning from Social Streams for Media Applications (Page 649)
Suman D. Roy (University of Missouri)
Tao Mei (Microsoft Research Asia)
Wenjun Zeng (University of Missouri)
Shipeng Li (Microsoft Research Asia)

Hybrid Social Media Network (Page 659)
Dong Liu (Columbia University)
Guangnan Ye (Columbia University)
Ching-Ting Chen (Columbia University)
Shuicheng Yan (National University of Singapore)
Shih-Fu Chang (Columbia University)

Discovering Informative Social Subgraphs and Predicting Pairwise Relationships from Group Photos (Page 669)
Yan-Ying Chen (National Taiwan University & Academia Sinica)
Winston H. Hsu (National Taiwan University)
Hong-Yuan Mark Liao (Academia Sinica)